Adversarial Domain Adaptation Research Articles

Similar norm more transferable: Rethinking feature norms discrepancy in adversarial domain adaptation

Adversarial learning has become an effective paradigm for learning transferable features in domain adaptation. However, many previous adversarial domain adaptation methods inevitably damage the discriminative information contained in transferable features, which limits the potential of adversarial learning. In this paper, we explore the reason for this phenomenon and find that the model pays more attention to the alignment of feature norms than the learning of domain-invariant features during adversarial adaptation. Moreover, we observe that the feature norms contain some crucial category information, which is ignored in previous studies. To achieve better adversarial adaptation, we propose two novel feature norms alignment strategies: Histogram-guided Norms Alignment (HNA) and Transport-guided Norms Alignment (TNA). Both strategies model the feature norms from the distribution perspective, which not only facilitates the reduction of the norms discrepancy but also makes full use of discriminative information contained in the norms. Extensive experiments demonstrate that progressively aligning the feature norms distributions of two domains can effectively promote the capture of semantically rich shared features and significantly boost the model’s transfer performance. We hope our findings can shed some light on future research of adversarial domain adaptation.

Enhancing Robustness of Surface Electromyography Pattern Recognition at Different Arm Positions for Transhumeral Amputees Using Deep Adversarial Inception Domain Adaptation

Enhancing Robustness of Surface Electromyography Pattern Recognition at Different Arm Positions for Transhumeral Amputees Using Deep Adversarial Inception Domain Adaptation

Fault severity recognition in axial piston pumps using attention-based adversarial discriminative domain adaptation neural network

Axial piston pumps are the ‘hearts’ of hydraulic systems whose fault recognition is necessary for the safety and reliability of hydraulic equipment. These pumps operate under different operating conditions and the fault recognition model trained at one operating point cannot be applicable at another operating point due to the problem of domain shifts. This paper proposes a transfer learning method for the fault severity recognition of axial piston pumps based on adversarial discriminative domain adaptation fused with a convolutional channel attention module. First, a convolutional neural network is pre-trained with labeled vibration data from the source domain, and a convolutional channel attention module is added to assign weights to different convolution kernels. Second, the trained source model is transferred to the target domain, and its parameters are updated by an adversarial training process between the labeled source data and the unlabeled target data. Finally, vibration data are collected from an axial piston pump at different fault levels under various operating conditions to validate the proposed method. Experimental results indicate that the proposed method achieves an average recognition accuracy of 98.3% and outperforms some other transfer learning methods by a large margin.

Contrastive domain-adaptive graph selective self-training network for cross-network edge classification

The performance of graph Neural Network (GNNs) can degrade significantly when trained on the graphs with noisy edges connecting nodes from different classes. To mitigate the negative effect of noisy edges, previous studies have largely focused on predicting the label agreement between node pairs within a single network. So far, predicting noisy edges across different networks remains largely underexplored. To bridge this gap, our work studies a novel problem of cross-network homophilous and heterophilous edge classification (CNHHEC), aiming to predict the label agreement of edges in an unlabeled target network by transferring the knowledge from a labeled source network. A novel Contrastive Domain-adaptive Graph Self-training Network (CDGSN) is proposed. Firstly, CDGSN learns node and edge embeddings end-to-end by a GNN encoder with adaptive edge weights during neighborhood aggregation. Secondly, to facilitate knowledge transfer across networks, CDGSN employs an adversarial domain adaptation module to align edge embeddings across networks, and also designs a novel contrastive domain adaptation module to conduct class-aware cross-network alignment of node embeddings. As a result, the intra-class domain divergence can be mitigated while the inter-class domain discrepancy can be enlarged to yield network-invariant and label-discriminative node and edge embeddings. Moreover, CDGSN designs a selective positive and negative pseudo-labeling strategy to assign positive (negative) pseudo-labels to the target nodes with extremely high (low) prediction confidence of belonging to each specific class. Such pseudo-labeled target nodes would be employed to iteratively re-train the model in a self-training manner, so as to obtain more reliable target pseudo-labels progressively to guide class-aware domain alignment. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed CDGSN on the CNHHEC problem. The performance of CDGSN is robust against various types of edge embeddings. When adopting three operators to construct edge embeddings, the proposed CDGSN can improve the state-of-the-art method for CNHHEC by an average of 0.5 %, 2.8 %, and 10.8 % in terms of AUC, and 1.3 %, 3.0 %, and 6.3 % in terms of AP, respectively.

Open-set adversarial domain match for electronic nose drift compensation and unknown gas recognition

In practical applications, electronic noses (EN) must tackle not only sensor drift but also resist interference from unknown gases. In prolonged open environments, electronic noses often encounter unknown gases that cannot be predicted in advance. Current gas detection methods typically rely on prior knowledge of target analytes but struggle to comprehensively address sensor drift and interference from unknown gases. Such as indoor air quality monitoring, long-term stability is crucial, and not all relevant analytes can be predetermined. However, the recent research cannot solve both the sensor drift and unknown gas intrusion problem simultaneously well. In this work, we unify above problems in to the open-set risk boundary. We propose an open-set adversarial domain match (OSADM) model and introduce the considers of open-set domain adaptation (OSDA). OSDA trains a target classifier through matching the domain distribution to recognize the known and unknown gases. First, a binary adversarial loss divides the class boundary. Secondly, adversarial domain adaptation unifies the distribution of different domains. Compared with the metric methods, it avoids complex distribution computation and parameter adjustment to reduce negative transfer. Extensive experimental results on two benchmark datasets, Gas Sensor Array Drift and Twin gas sensor arrays Dataset show that OSADM outperformance of the existing open-set models.

Simulation-driven fault detection for the gear transmission system in major equipment

Scholars and engineers attach great importance to fault detection in mechanical systems due to the unpredictable faults that arise from long-term operations under complex and extreme conditions. The fact that each type of fault embodies unique characteristics makes it challenging to obtain sufficient fault samples, and conventional machine learning methods fail to provide satisfactory fault diagnosis results. To address this issue, a simulation-driven fault detection method has been proposed in this paper. Firstly, the DT model of the gear transmission system was established. An improved multi-objective sparrow search algorithm (MOSSA) was employed to update the model and obtain an adequate number of simulation fault samples as well. Secondly, a two-stage adversarial domain adaptation model with full-scale feature fusion (ADAM-FF) was utilized to align and integrate the features of simulated and generated fault samples. This enables model training and classification of combined samples, facilitating the detection of unknown faults in actual measurements. Lastly, a simulation-driven equipment health index assessment model which accurately and non-destructively evaluates the degradation status of the equipment was introduced. This model effectively quantifies the extent of equipment degradation, thereby facilitating the transfer from the simulation realm to practical engineering applications. To validate the effectiveness of the proposed fault detection method, an experimental study was conducted on the extruder gear reducer of a petrochemical enterprise. The proposed fault detection method has the potential for widespread application across a range of large-scale mechanical equipment. As such, the utilization of this method will enable proactive maintenance planning, ensure safe and stable equipment operations, and minimize energy loss.

Transfer Learning for Bearing Fault Diagnosis based on Graph Neural Network with Dilated KNN and Adversarial Discriminative Domain Adaptation

Graph neural networks (GNNs) have emerged as a forefront in deep learning, notably influencing research in mechanical fault diagnosis. Transfer learning, particularly through domain adaptation (DA) techniques, has found application in machinery fault diagnosis by training models under one working condition and deploying them under another. While efforts have been made to integrate GNNs with DA techniques to alleviate data distribution discrepancies by investigating the inter-sample relationships, challenges persist: reliance on K-nearest neighbor (KNN) for graph generation emphasizes close relationships, neglecting distant ones; batch processing limits real-time fault diagnosis; and transfer between different-sized bearings is nearly unexplored. To address these limitations, a novel framework for GNN-based domain adaptation in machinery fault diagnosis is proposed. Initially, a convolutional neural network extracts node embeddings from the continuous wavelet transform graph of raw vibration signals. Subsequently, a graph generation layer based on dilated KNN captures both close and distant sample relationships, addressing the long-range dependency issue. Two GNN blocks are then applied for inter-sample relationships investigation and further feature extraction with the outputs directed to a linear classifier during source domain pretraining. Following pretraining, adversarial discriminative domain adaptation is leveraged to mitigate domain distribution discrepancies. Additionally, a novel graph construction method that combines existing training samples with a new single sample is proposed, enabling fault prediction with single instances for real-time online fault diagnosis. Evaluation on datasets with varying working conditions and bearings of different sizes demonstrates the superior performance of our method to other comparison methods.

Unsupervised and Semi-Supervised Robust Spherical Space Domain Adaptation.

Adversarial domain adaptation has been an effective approach for learning domain-invariant features by adversarial training. In this paper, we propose a novel adversarial domain adaptation approach defined in the spherical feature space, in which we define spherical classifier for label prediction and spherical domain discriminator for discriminating domain labels. In the spherical feature space, we develop a spherical robust pseudo-label loss to utilize pseudo-labels robustly, which weights the importance of the estimated labels of target domain data by the posterior probability of correct labeling, modeled by the Gaussian-uniform mixture model in the spherical space. Our proposed approach can be generally applied to both unsupervised and semi-supervised domain adaptation settings. In particular, to tackle the semi-supervised domain adaptation setting where a few labeled target domain data are available for training, we propose a novel reweighted adversarial training strategy for effectively reducing the intra-domain discrepancy within the target domain. We also present theoretical analysis for the proposed method based on the domain adaptation theory. Extensive experiments are conducted on multiple benchmarks for object recognition, digit recognition, and face recognition. The results show that our method either surpasses or is competitive compared with the recent methods for both unsupervised and semi-supervised domain adaptation. Ablation studies also confirm the effectiveness of the spherical classifier, spherical discriminator, spherical robust pseudo-label loss, and reweighted adversarial training strategy.

Overcoming the lack of labeled data: Training malware detection models using adversarial domain adaptation

Many current malware detection methods are based on supervised learning techniques, which however have certain limitations. First, these techniques require a large amount of labeled data for training which is often difficult to obtain. Second, they are not very effective when there are differences in domain distribution between new malware and known malware. To address these issues, we propose MD-ADA – a malware detection framework that leverages adversarial domain adaptation (DA). DA allows one to adapt a training malware dataset available at a domain, referred to as the source, for training a classifier in another domain, referred to as the target. DA, typically used when the target has limited training malware data available, maps the source and target datasets into a common latent space. As we use an image representation for malware binaries, MD-ADA uses a convolution neural network (CNN) providing a lossless image embedding for the source and target datasets. MD-ADA also employs a generative adversarial network (GAN) for malware classification that is suitable for scenarios with few target-labeled data where the distribution of the features is similar (homogeneous) or different (heterogeneous). We have carried out several experiments to assess the performance of MD-ADA. The experiments show that MD-ADA outperforms the fine-tuning approach with an accuracy of 99.29% on the BODMAS dataset, 89.3% for the Malevis dataset on homogeneous feature distribution, and 90.12% on the CICMalMem2022 dataset (Target) and 83.23% on the Microsoft Kaggle dataset (Target) for heterogeneous feature distribution. The observed F1-scores of 99.13% and 87.5% for homogeneous feature distributions and 91.27% and 81.7% for heterogeneous distributions indicate that the MD-ADA performance is satisfactory for both data distributions when the target has very few labeled data.

Electronic Nose Drift Suppression Based on Smooth Conditional Domain Adversarial Networks.

Anti-drift is a new and serious challenge in the field related to gas sensors. Gas sensor drift causes the probability distribution of the measured data to be inconsistent with the probability distribution of the calibrated data, which leads to the failure of the original classification algorithm. In order to make the probability distributions of the drifted data and the regular data consistent, we introduce the Conditional Adversarial Domain Adaptation Network (CDAN)+ Sharpness Aware Minimization (SAM) optimizer-a state-of-the-art deep transfer learning method.The core approach involves the construction of feature extractors and domain discriminators designed to extract shared features from both drift and clean data. These extracted features are subsequently input into a classifier, thereby amplifying the overall model's generalization capabilities. The method boasts three key advantages: (1) Implementation of semi-supervised learning, thereby negating the necessity for labels on drift data. (2) Unlike conventional deep transfer learning methods such as the Domain-adversarial Neural Network (DANN) and Wasserstein Domain-adversarial Neural Network (WDANN), it accommodates inter-class correlations. (3) It exhibits enhanced ease of training and convergence compared to traditional deep transfer learning networks. Through rigorous experimentation on two publicly available datasets, we substantiate the efficiency and effectiveness of our proposed anti-drift methodology when juxtaposed with state-of-the-art techniques.

Multibolt looseness monitoring of steel structure based on multitask active sensing method and substructure cross-domain transfer learning

Under the influence of service life and the external environment, bolted connections are prone to loosening, which may lead to structural hazards. Thus, it is crucial to carry out real-time monitoring of bolted connections. Based on the active sensing method, previous researchers mainly focused on quantifying the single-bolt looseness, with little focus on locating and quantifying the multibolted connection. This study introduces an innovative approach to monitor multibolt looseness in steel structures. The proposed method utilizes multitask active sensing, incorporating a substructure cross-domain transfer learning technique. A finite-element model of a portal frame structure was first established by ABAQUS software, and the substructure was determined based on the stress wave propagation characteristics. Secondly, the location and degree of bolted connection in the substructure and portal frame structure were monitored using the piezoelectric active sensing method. Monitoring data of the substructure are tagged as the source domain, while data of the portal frame structure are tagged as the target domain. To efficiently decouple the characteristics of loosening, this study extracted multidomain energy and unthresholded multivariate recurrence plots from stress wave signals. These elements were employed to pinpoint the location and assess the degree of looseness. The multibolted connection was then monitored by the adversarial domain adaptation networks. Ultimately, using the target domain’s input, the optimized model was able to precisely detect the location and degree of the multibolted connection step by step. The experimental results demonstrated that the suggested technique has a lot of promise for multibolt looseness monitoring.

Confounder balancing in adversarial domain adaptation for pre-trained large models fine-tuning

The excellent generalization, contextual learning, and emergence abilities in the pre-trained large models (PLMs) handle specific tasks without direct training data, making them the better foundation models in the adversarial domain adaptation (ADA) methods to transfer knowledge learned from the source domain to target domains. However, existing ADA methods fail to account for the confounder properly, which is the root cause of the source data distribution that differs from the target domains. This study proposes a confounder balancing method in adversarial domain adaptation for PLMs fine-tuning (CadaFT), which includes a PLM as the foundation model for a feature extractor, a domain classifier and a confounder classifier, and they are jointly trained with an adversarial loss. This loss is designed to improve the domain-invariant representation learning by diluting the discrimination in the domain classifier. At the same time, the adversarial loss also balances the confounder distribution among source and unmeasured domains in training. Compared to newest ADA methods, CadaFT can correctly identify confounders in domain-invariant features, thereby eliminating the confounder biases in the extracted features from PLMs. The confounder classifier in CadaFT is designed as a plug-and-play and can be applied in the confounder measurable, unmeasurable, or partially measurable environments. Empirical results on natural language processing and computer vision downstream tasks show that CadaFT outperforms the newest GPT-4, LLaMA2, ViT and ADA methods.

Unsupervised Logo Detection Using Adversarial Learning From Synthetic to Real Images

Most existing deep learning-based methods for logo detection require a large amount of object-level annotated training data. However, it takes a lot of time and effort to create a good object-level annotated logo detection dataset. Many researchers have tried to utilize synthesized images with automatically generated annotations for training to deal with data annotation problem. However, in real applications, model trained using synthesized images suffer from performance loss due to domain shift between synthesized and real-world images. To this end, in this paper, we propose an adversarial learning-based unsupervised domain adaptation method for logo detection. We only use labeled synthesized logo images for model training and adapt target domain knowledge using unlabeled real-world logo images. We propose entropy minimization of mid-level output feature maps in order to effectively align the domain gap between synthetic and real images for the logo detection task. Additionally, we have generated coherent synthesized logo images with automatically constructed bounding box annotations for different datasets to perform unsupervised training for the experiments. Our experiments show that the proposed method improves performance on different logo datasets compared to direct transfer from source to target domain (synthetic-to-real images) without any labeling cost and increasing network parameters.

Recognition of grinding surface roughness grade based on adversarial domain adaptation under variable illumination

End-to-end roughness measurement can be achieved through the self-extraction of grinding surface features, which can be achieved through deep learning. However, due to the grinding surface texture being random, the features are weak, the self-extracted grinding surface features of the same surface under different lighting environments are different, and the training data and the test data when the lighting environments are inconsistent with the recognition of the measurement of the precision of the lower. To tackle these problems, this paper proposes an adversarial domain self-adaptation (NMDANN) based visual measurement method for grinding surface roughness under variable illumination. An improved residual network is used as a generator to extract more effective metastable features, and multi-head attention is introduced into the domain discriminator to enhance its domain adaptive capability. The experimental results show that the method can achieve an average recognition precision of 96.9112% for different grades of roughness on the grinding surface under the changing light environment, which is 40.1360% higher than the ordinary classification model ResNet50 and 10.1626% higher than the DANN model with migration capability. It lays the foundation for the online visual measurement of roughness on the grinding surface under the variable light environment. This lays the foundation for the online visualization of grinding surface roughness measurement in variable light environments.

Adversarial learning-based domain adaptation algorithm for intracranial artery stenosis detection on multi-source datasets

Intracranial arterial stenosis (ICAS) is characterized by the pathological narrowing or occlusion of the inner lumen of intracranial blood vessels. However, the retina can indirectly react to cerebrovascular disease. Therefore, retinal fundus images (RFI) serve as valuable noninvasive and easily accessible screening tools for early detection and diagnosis of ICAS. This paper introduces an adversarial learning-based domain adaptation algorithm (ALDA) specifically designed for ICAS detection in multi-source datasets. The primary objective is to achieve accurate detection and enhanced generalization of ICAS based on RFI. Given the limitations of traditional algorithms in meeting the accuracy and generalization requirements, ALDA overcomes these challenges by leveraging RFI datasets from multiple sources and employing the concept of adversarial learning to facilitate feature representation sharing and distinguishability learning. In order to evaluate the performance of the ALDA algorithm, we conducted experimental validation on multi-source datasets. We compared its results with those obtained from other deep learning algorithms in the ICAS detection task. Furthermore, we validated the potential of ALDA for detecting diabetic retinopathy. The experimental results clearly demonstrate the significant improvements achieved by the ALDA algorithm. By leveraging information from diverse datasets, ALDA learns feature representations that exhibit enhanced generalizability and robustness. This makes it a reliable auxiliary diagnostic tool for clinicians, thereby facilitating the prevention and treatment of cerebrovascular diseases.

Online lithium battery SOC estimation based on adversarial domain adaptation under a small sample dilemma

Online lithium battery SOC estimation based on adversarial domain adaptation under a small sample dilemma

Dynamic Weighted Adversarial Learning for Semi-Supervised Classification under Intersectional Class Mismatch

Nowadays, class-mismatch problem has drawn intensive attention in Semi-Supervised Learning (SSL), where the classes of labeled data are assumed to be only a subset of the classes of unlabeled data. However, in a more realistic scenario, the labeled data and unlabeled data often share some common classes while they also have their individual classes, which leads to an “intersectional class-mismatch” problem. As a result, existing SSL methods are often confused by these individual classes and suffer from performance degradation. To address this problem, we propose a novel Dynamic Weighted Adversarial Learning (DWAL) framework to properly utilize unlabeled data for boosting the SSL performance. Specifically, to handle the influence of the individual classes in unlabeled data (i.e., Out-Of-Distribution classes), we propose an enhanced adversarial domain adaptation to dynamically assign weight for each unlabeled example from the perspectives of domain adaptation and a class-wise weighting mechanism, which consists of transferability score and prediction confidence value. Besides, to handle the influence of the individual classes in labeled data (i.e., private classes), we propose a dissimilarity maximization strategy to suppress the inaccurate correlations caused by the examples of individual classes within labeled data. Therefore, our DWAL can properly make use of unlabeled data to acquire an accurate SSL classifier under intersectional class-mismatch setting, and extensive experimental results on five public datasets demonstrate the effectiveness of the proposed model over other state-of-the-art SSL methods.

Source-free domain adaptation with unrestricted source hypothesis

Domain adaptation aims to bridge the distribution discrepancy across different domains and improve the generalization ability of learning models on the target domain. The existing domain adaptation approaches align the distribution shift via adversarial training on the source and target data. In practice, however, the source data is usually unavailable due to the privacy factor. In this work, we mainly focus on the source-free domain adaptation setting, in which we are only accessible to the model trained on the source data and the unlabeled target data. To this end, we propose the Source-Free Adversarial Domain Adaptation (SFADA) approach to align the distribution of the target domain data in the absence of source domain data. In particular, we develop an effective metric to measure the domain discrepancy by introducing the proxy data of the source domain. To generate the proxy data, our approach retrieves target data which lie over the intersection of the supports of the source and target domains. We also derive the learning bound of the source-free domain adaptation theoretically and show that our proposed SFADA approach is capable of reducing the bound effectively. Additionally, instead of modifying the source model in previous source-free approaches, our SFADA does not require training the source model with specific restrictions (i.e., normalizing the classifier weight) for practice and privacy-related concerns. State-of-the-art results are achieved for different standard domain adaptation benchmarks. The code can be available from https://github.com/tiggers23/SFADA-main.

Neural network approach for shape-based euhedral pyrite identification in X-ray CT data with adversarial unsupervised domain adaptation

We explore an attenuation and shape-based identification of euhedral pyrites in high-resolution X-ray Computed Tomography (XCT) data using deep neural networks. To deal with the scarcity of annotated data we generate a complementary training set of synthetic images. To investigate and address the domain gap between the synthetic and XCT data, several deep learning models, with and without domain adaption, are trained and compared. We find that a model trained on a small set of human annotations, while displaying over-fitting, can rival the human annotators. The unsupervised domain adaptation approaches are successful in bridging the domain gap, which significantly improves their performance. A domain-adapted model, trained on a dataset that fuses synthetic and real data, is the overall best-performing model. This highlights the possibility of using synthetic datasets for the application of deep learning in mineralogy.

Privacy-preserving Federated Adversarial Domain Adaptation over Feature Groups for Interpretability

We present a novel privacy-preserving federated adversarial domain adaptation approach ($\textbf{PrADA}$) to address an under-studied but practical cross-silo federated domain adaptation problem, in which the party of the target domain is insufficient in both samples and features. We address the lack-of-feature issue by extending the feature space through vertical federated learning with a feature-rich party and tackle the sample-scarce issue by performing adversarial domain adaptation from the sample-rich source party to the target party. In this work, we focus on financial applications where interpretability is critical. However, existing adversarial domain adaptation methods typically apply a single feature extractor to learn feature representations that are low-interpretable with respect to the target task. To improve interpretability, we exploit domain expertise to split the feature space into multiple groups that each holds relevant features, and we learn a semantically meaningful high-order feature from each feature group. In addition, we apply a feature extractor (along with a domain discriminator) for each feature group to enable a fine-grained domain adaptation. We design a secure protocol that enables performing the PrADA in a secure and efficient manner. We evaluate our approach on two tabular datasets. Experiments demonstrate both the effectiveness and practicality of our approach.